From 71e54b9ecd39b6e984ab239a4267a97f07312537 Mon Sep 17 00:00:00 2001 From: Steve Androulakis Date: Thu, 29 May 2025 08:26:16 -0700 Subject: [PATCH] todo list (#38) * Update todo.md --- todo.md | 49 ++++++++++++++++++++++++++++--------------------- 1 file changed, 28 insertions(+), 21 deletions(-) diff --git a/todo.md b/todo.md index 4e4e611..10d7663 100644 --- a/todo.md +++ b/todo.md @@ -1,8 +1,33 @@ # todo list -[x] take steve's confirm box changes https://temporaltechnologies.slack.com/archives/D062SV8KEEM/p1745251279164319
-[ ] consider adding goal categories to goal picker -[ ] adding fintech goals
+## General Agent Enhancements + +[ ] MCP: There is a plan to add MCP (Model Context Protocol) to the agent. This really really really needs to be done and is scheduled to be done by @steveandroulakis some time in June 2025. + +[ ] Google's A2A is emerging as the standard way to hand off agents to other agents. We should examine implementing this soon. + +[ ] Custom metrics/tracing is important for AI specific aspects such as number of LLM calls, number of bad LLM responses that require retrying, number of bad chat outcomes. We should add this. + +[ ] Evals are very important in agents. We want to be able to 'judge' the agent's performance both in dev and production (AIOps). This will help us improve our agent's performance over time in a targeted fashion. + +[ ] Dynamically switch LLMs on persistent failures:
+ - detect failure in the activity using failurecount
+ - activity switches to secondary LLM defined in .env + - activity reports switch to workflow + +[ ] Collapse history/summarize chat after goal finished
+ +[ ] Write tests
+ +[ ] non-retry the api key error - "Invalid API Key provided: sk_test_**J..." and "AuthenticationError"
+ +[ ] add visual feedback when workflow starting
+ +[ ] enable user to list agents at any time - like end conversation - probably with a next step
+ +## Ideas for more goals and tools + +[ ] Add fintech goals
- Fraud Detection and Prevention - The AI monitors transactions across accounts, flagging suspicious activities (e.g., unusual spending patterns or login attempts) and autonomously freezing accounts or notifying customers and compliance teams.
- Personalized Financial Advice - An AI agent analyzes a customer’s financial data (e.g., income, spending habits, savings, investments) and provides tailored advice, such as budgeting tips, investment options, or debt repayment strategies.
- Portfolio Management and Rebalancing - The AI monitors a customer’s investment portfolio, rebalancing it automatically based on market trends, risk tolerance, and financial goals (e.g., shifting assets between stocks, bonds, or crypto).
@@ -12,21 +37,3 @@ [ ] tool is maybe a new tool asking the LLM to advise [ ] for demo simulate failure - add utilities/simulated failures from pipeline demo
- -[ ] LLM failure->autoswitch:
- - detect failure in the activity using failurecount
- - activity switches to secondary LLM defined in .env - - activity reports switch to workflow - -[ ] for demo simulate failure - add utilities/simulated failures from pipeline demo
- -[ ] expand [tests](./tests/agent_goal_workflow_test.py)
-[ ] collapse history/summarize after goal finished
-[ ] add aws bedrock
- -[ ] ask the ai agent how it did at the end of the conversation, was it efficient? successful? insert a search attribute to document that before return
-- Insight into the agent’s performance
-[ ] non-retry the api key error - "Invalid API Key provided: sk_test_**J..." and "AuthenticationError"
-[ ] add visual feedback when workflow starting
-[ ] enable user to list agents at any time - like end conversation - probably with a next step
- - with changing "'Next should only be "pick-new-goal" if all tools have been run (use the system prompt to figure that out).'" in [prompt_generators](./prompts/agent_prompt_generators.py). \ No newline at end of file